CN108833967A - A kind of rapid section method based on video - Google Patents
A kind of rapid section method based on video Download PDFInfo
- Publication number
- CN108833967A CN108833967A CN201810734058.7A CN201810734058A CN108833967A CN 108833967 A CN108833967 A CN 108833967A CN 201810734058 A CN201810734058 A CN 201810734058A CN 108833967 A CN108833967 A CN 108833967A
- Authority
- CN
- China
- Prior art keywords
- target
- video
- moving target
- time
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/4402—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving reformatting operations of video signals for household redistribution, storage or real-time display
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
- H04N21/4325—Content retrieval operation from a local storage medium, e.g. hard-disk by playing back content from the storage medium
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8547—Content authoring involving timestamps for synchronizing content
Abstract
A kind of rapid section method based on video,The flow data of video is obtained using Open-Source Tools FFMPEG,The decoding interval time is then arranged by the time in camera head monitor region according to inquiry target,And the flow data of the decoding time intervals of setting and video is passed in CUDA decoder,It is quickly decoded by CUDA decoder,And decoded picture is enumerated,Pass through artificial On-line monitor,The picture comprising inquiry target is selected from the picture enumerated,And then determine moving target,Determining moving target is being extracted in the track following that target zone carries out with color,Finally movement objective orbit tracking is showed in a manner of video segment,Target entrance and the out slice of camera lens are embodied emphatically,Greatly reduce the video backtracking time,Video time is consulted to reduce staff,Accelerate working efficiency,Reduce the waste of manpower and resource.
Description
Technical field
The present invention relates to mode identification technology more particularly to a kind of rapid section methods based on video.
Background technique
With economical continuous development and social progress, social safety is put on critically important position.In order to preferably
Safeguard social safety, in recent years, country has sequentially activated the projects such as safe city, day net engineering, by city streets and lanes Dou Na
Enter into supervision of the cities, monitors throughout each corner in city, a large amount of camera is while realizing supervision of the cities
The video big data of magnanimity is produced, because the generation and retrospect of case have hysteresis quality, personnel in charge of the case, which can only lead to, to be gone over all over looking into
Video is read, suspicious object is therefrom found out, this is the process of a time-consuming and labor intensive, is also easy to miss and most preferably solve a case the time.
Summary of the invention
Technical problem solved by the invention is to provide a kind of rapid section method based on video, to solve above-mentioned back
Disadvantage in scape technology.
Technical problem solved by the invention is realized using following technical scheme:
A kind of rapid section method based on video, specific step is as follows:
1)The flow data of video is obtained first with Open-Source Tools FFMPEG, the video format that wherein Open-Source Tools FFMPEG is supported
Including MPEG/.MPG/.DAT/. AVI/. RA/RM/RAM;
2)The decoding interval time is arranged by the time in camera head monitor region according to inquired target, such as:It needs to inquire
Target is behaved, and the time that people passes through camera head monitor region on foot is 1min, therefore the decoding interval time is set as being slightly less than
1min, the frame per second of video choose the interval for being less than 1min in 25 frames/s, decoded picture, there is that there are targets on a frame picture;
3)The flow data of the decoding time intervals of setting and video is passed in CUDA decoder, is carried out using CUDA decoder fast
Speed decoding, and decoded picture is enumerated;
4)By artificial On-line monitor, the picture comprising inquiry target is selected from the picture enumerated, and then combines the figure of front and back
Piece, to determine that moving target enters the time range in camera head monitor region;
5)Background is established using VIBE algorithm according to the time range of confirmation target, by the matching to background template, thus
Confirm moving target;
6)Based on morphology mode, to step 5)The moving target pixel of middle confirmation is first expanded post-etching, so that connection
There is no empty windows to remove noise jamming simultaneously between domain, accurately to extract moving target;To the moving target of extraction in target
The track following that range carries out is extracted with color;Wherein, track following takes Meanshift algorithm, and color extraction is taken
The method of statistics with histogram, the range of Query on color is using RGA color gamut as foundation, using the centroid of moving target as separation,
Facilitating differentiation target is the dressing of people at that time, such as:Inquire target behave, above the waist dress be white shirt, under as black
Trousers show as black below centroid then the above color of centroid shows as white;
7)By step 6)The track following of middle moving target is showed in a manner of video segment, embodies target entrance and appearance emphatically
The slice of head, and by target trajectory timestamp, moving target size, the storage of moving target color characteristic into database, work
Personnel can realize the quick backtracking of video according to inquiry target signature.
Beneficial effect:The present invention obtains the flow data of video using Open-Source Tools FFMPEG, then logical according to inquiry target
It setting decoding interval time time for crossing camera head monitor region, is quickly decoded by CUDA decoder, and to decoded
Picture is enumerated, and by artificial On-line monitor, the picture comprising inquiry target is selected from the picture enumerated, and then determine fortune
Moving-target, finally showed in a manner of video segment movement objective orbit tracking, is embodied target emphatically and is entered and camera lens out
Slice greatly reduces the video backtracking time, so that reducing staff consults video time, accelerates working efficiency, reduces people
The waste of power and resource.
Detailed description of the invention
Fig. 1 is the flow diagram of presently preferred embodiments of the present invention.
Specific embodiment
In order to be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, tie below
Conjunction is specifically illustrating, and the present invention is further explained.
A kind of rapid section method based on video shown in Figure 1, specific step is as follows:
1)The flow data of video is obtained first with Open-Source Tools FFMPEG, wherein Open-Source Tools FFMPEG supports common video
Format MPEG/.MPG/.DAT/. AVI/. RA/RM/RAM etc.;
2)The decoding interval time is arranged by the time in camera head monitor region according to inquired target, such as:It needs to inquire
Target is behaved, and the time that people passes through camera head monitor region on foot is 1min, therefore the decoding interval time is set as being slightly less than
1min, the frame per second of video choose the interval for being less than 1min in 25 frames/s, decoded picture, there is that there are targets on a frame picture;
3)The flow data of the decoding time intervals of setting and video is passed in CUDA decoder, is carried out using CUDA decoder fast
Speed decoding, and decoded picture is enumerated;
4)By artificial On-line monitor, the picture comprising inquiry target is selected from the picture enumerated, and then combines the figure of front and back
Piece, to determine that moving target enters the time range in camera head monitor region;
5)Background is established using VIBE algorithm according to the time range of confirmation target, by the matching to background template, thus
Confirm moving target;
VIBE algorithm extracts moving target:Using statistics rule, the number of the value of each pixel of single frames picture is counted, is passed through
Continuous frame image establishes background model(Each pixel 20 values), hereafter, the size of every each pixel value of frame picture is counted,
If they are the same in the pixel value of position and its nine grids there are two pixel value is equal with background model, i.e., identification is background, other pictures
Plain value then assert it is moving target;
6)Based on morphology mode, to step 5)The moving target pixel of middle confirmation is first expanded post-etching, so that connection
There is no empty windows to remove noise jamming simultaneously between domain, accurately to extract moving target;To the moving target of extraction in target
The track following that range carries out is extracted with color;Wherein, track following takes Meanshift algorithm, and color extraction is taken
The method of statistics with histogram, the range of Query on color is using RGA color gamut as foundation, using the centroid of moving target as separation,
Facilitating differentiation target is the dressing of people at that time, such as:Inquire target behave, above the waist dress be white shirt, under as black
Trousers show as black below centroid then the above color of centroid shows as white;
7)By step 6)The track following of middle moving target is showed in a manner of video segment, embodies target entrance and appearance emphatically
The slice of head, and by target trajectory timestamp, moving target size, the storage of moving target color characteristic into database, work
Personnel can realize the quick backtracking of video according to inquiry target signature.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (6)
1. a kind of rapid section method based on video, which is characterized in that specific step is as follows:
1)The flow data of video is obtained first with Open-Source Tools FFMPEG;
2)The decoding interval time is arranged by the time in camera head monitor region according to inquired target;
3)The flow data of the decoding time intervals of setting and video is passed in CUDA decoder, is carried out using CUDA decoder fast
Speed decoding, and decoded picture is enumerated;
4)By artificial On-line monitor, the picture comprising inquiry target is selected from the picture enumerated, and then combines the figure of front and back
Piece, to determine that moving target enters the time range in camera head monitor region;
5)According to the time range of confirmation target, background is established using VIBE algorithm, by being matched to background template, thus
Confirm moving target;
6)To step 5)Determining moving target is extracted in the track following that target zone carries out with color;
7)By step 6)Middle movement objective orbit tracking is showed in a manner of video segment, embodies target entrance and out camera lens emphatically
Slice, and by target trajectory timestamp, moving target size, moving target color characteristic storage into database, work people
Member can realize the quick backtracking of video according to inquiry target signature.
2. a kind of rapid section method based on video according to claim 1, which is characterized in that step 1)In, open source
The video format that tool FFMPEG is supported includes MPEG/.MPG/.DAT/. AVI/. RA/RM/RAM.
3. a kind of rapid section method based on video according to claim 1, which is characterized in that step 2)In, decoding
Interval time setting is less than the time that inquired target passes through camera head monitor region.
4. a kind of rapid section method based on video according to claim 1, which is characterized in that step 5)In, it uses
It is to count the number of the value of each pixel of single frames picture using statistics rule, lead to that VIBE algorithm, which extracts moving target step,
It crosses continuous frame image and establishes background model, hereafter, count the size of every each pixel value of frame picture, if they are the same the pixel of position
Pixel value is equal with background model there are two in value and its nine grids, that is, assert it is background, and it is movement that other pixel values, which are then assert,
Target.
5. a kind of rapid section method based on video according to claim 1, which is characterized in that step 6)In, subject to
Moving target really is extracted, morphology mode is based on, to step 5)The moving target pixel of middle confirmation carries out rotten after first expanding
Erosion, so that there is no empty windows to remove noise jamming simultaneously between connected domain.
6. a kind of rapid section method based on video according to claim 1, which is characterized in that step 6)In, wherein
Track following takes Meanshift algorithm, and the method that color extraction takes statistics with histogram, the range of Query on color is with RGA face
Color range is foundation, using the centroid of moving target as separation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810734058.7A CN108833967A (en) | 2018-07-06 | 2018-07-06 | A kind of rapid section method based on video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810734058.7A CN108833967A (en) | 2018-07-06 | 2018-07-06 | A kind of rapid section method based on video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108833967A true CN108833967A (en) | 2018-11-16 |
Family
ID=64136204
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810734058.7A Pending CN108833967A (en) | 2018-07-06 | 2018-07-06 | A kind of rapid section method based on video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108833967A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040105570A1 (en) * | 2001-10-09 | 2004-06-03 | Diamondback Vision, Inc. | Video tripwire |
CN103020981A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Rapid key frame extraction algorithm based on video moving target |
CN104796756A (en) * | 2014-01-20 | 2015-07-22 | 三星泰科威株式会社 | Image recording system |
CN106845373A (en) * | 2017-01-04 | 2017-06-13 | 天津大学 | Towards pedestrian's attribute forecast method of monitor video |
CN107153820A (en) * | 2017-05-10 | 2017-09-12 | 电子科技大学 | A kind of recognition of face and movement locus method of discrimination towards strong noise |
CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技(深圳)有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
CN108012117A (en) * | 2017-11-30 | 2018-05-08 | 江西洪都航空工业集团有限责任公司 | A kind of city based on background modeling is set up a stall detection method |
-
2018
- 2018-07-06 CN CN201810734058.7A patent/CN108833967A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040105570A1 (en) * | 2001-10-09 | 2004-06-03 | Diamondback Vision, Inc. | Video tripwire |
CN103020981A (en) * | 2011-09-20 | 2013-04-03 | 佳都新太科技股份有限公司 | Rapid key frame extraction algorithm based on video moving target |
CN104796756A (en) * | 2014-01-20 | 2015-07-22 | 三星泰科威株式会社 | Image recording system |
CN106845373A (en) * | 2017-01-04 | 2017-06-13 | 天津大学 | Towards pedestrian's attribute forecast method of monitor video |
CN107153820A (en) * | 2017-05-10 | 2017-09-12 | 电子科技大学 | A kind of recognition of face and movement locus method of discrimination towards strong noise |
CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技(深圳)有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
CN108012117A (en) * | 2017-11-30 | 2018-05-08 | 江西洪都航空工业集团有限责任公司 | A kind of city based on background modeling is set up a stall detection method |
Non-Patent Citations (1)
Title |
---|
陈星明,廖娟,李勃,陈启美: "动态背景下基于改进视觉背景提取的前景检测", 《光学 精密工程》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2013189465A3 (en) | Method, device and system for obtaining the number of persons | |
CN106203513A (en) | A kind of based on pedestrian's head and shoulder multi-target detection and the statistical method of tracking | |
WO2018223554A1 (en) | Multi-source video clipping and playing method and system | |
CN103475882B (en) | Surveillance video encoding and recognizing method and surveillance video encoding and recognizing system | |
WO2020169121A3 (en) | Automatic video editing method and portable terminal | |
WO2013189464A2 (en) | Pedestrian tracking and counting method and device for near-front top-view monitoring video | |
CN107137886B (en) | A kind of football technique blank model and its construction method and application based on big data | |
CN109145736B (en) | A kind of detection method that the subway station pedestrian based on video analysis inversely walks | |
CN102867177A (en) | People number counting method based on image grey level matching | |
CN110049345A (en) | A kind of multiple video strems director method and instructor in broadcasting's processing system | |
CN106296677A (en) | A kind of remnant object detection method of double mask context updates based on double-background model | |
CN109766743A (en) | A kind of intelligent bionic policing system | |
CN110633648A (en) | Face recognition method and system in natural walking state | |
CN108833967A (en) | A kind of rapid section method based on video | |
Shu et al. | Small moving object detection and tracking based on event signals | |
CN104539875A (en) | Video monitoring method and system | |
CN107644431A (en) | Effective method for concentration of video monitoring in the case of a kind of low-light (level) | |
CN102306153A (en) | Method for detecting goal events based on normalized semantic weighting and regular football video | |
CN103914850B (en) | Automatic video labeling method and system based on motion matching | |
CN102393909B (en) | Method for detecting goal events in soccer video based on hidden markov model | |
CN103106633A (en) | Method and system of visual front view article screenshot based on gaussian mixture model | |
CN106408588A (en) | Field-goal percentage influence factor analysis method based on image processing technology | |
CN104935825A (en) | Method and system for processing images in tennis match | |
CN109584217B (en) | Automatic judging method for monitoring camera lens pollution | |
Kurano et al. | Ball trajectory extraction in team sports videos by focusing on ball holder candidates for a play search and 3D virtual display system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181116 |
|
RJ01 | Rejection of invention patent application after publication |